INDEX

Explanations

phrases indicating movement or transition from one place to another

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Motorsport

-0.67

 Vaugh

-0.62

 Citiz

-0.61

Shy

-0.60

 Rockets

-0.60

 Scarlett

-0.60

humans

-0.60

Cyp

-0.60

UR

-0.60

SX

-0.59

POSITIVE LOGITS

 lobe

0.81

worldly

0.81

 baseman

0.80

 wart

0.77

isphere

0.77

inant

0.76

dayName

0.76

heastern

0.73

 vowel

0.72

 consecut

0.71

Activations Density 0.084%

phrases indicating movement or transition from one place to another

No Comments

No Known Activations